{"id":"https://openalex.org/W3128311069","doi":"https://doi.org/10.1109/icassp39728.2021.9413711","title":"CDPAM: Contrastive Learning for Perceptual Audio Similarity","display_name":"CDPAM: Contrastive Learning for Perceptual Audio Similarity","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3128311069","doi":"https://doi.org/10.1109/icassp39728.2021.9413711","mag":"3128311069"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413711","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413711","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.05109","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075510192","display_name":"Pranay Manocha","orcid":"https://orcid.org/0000-0003-3284-5908"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pranay Manocha","raw_affiliation_strings":["Princeton University,USA","Princeton University, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University,USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Princeton University, USA#TAB#","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702050","display_name":"Zeyu Jin","orcid":"https://orcid.org/0000-0003-0161-5915"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyu Jin","raw_affiliation_strings":["Adobe Research,USA","[Adobe Research, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research,USA","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"[Adobe Research, USA]","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101616527","display_name":"Richard Zhang","orcid":"https://orcid.org/0000-0001-7712-1247"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Zhang","raw_affiliation_strings":["Adobe Research,USA","[Adobe Research, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research,USA","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"[Adobe Research, USA]","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034842939","display_name":"Adam Finkelstein","orcid":"https://orcid.org/0000-0001-9422-5363"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Finkelstein","raw_affiliation_strings":["Princeton University,USA","Princeton University, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University,USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Princeton University, USA#TAB#","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"196","last_page":"200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.7536342144012451},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7482059001922607},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6175520420074463},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5958210229873657},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5724350214004517},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5420215725898743},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.5278246998786926},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5264670848846436},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4952675402164459},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4405374228954315},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33823636174201965},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2132813036441803},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13985782861709595}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7536342144012451},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7482059001922607},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6175520420074463},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5958210229873657},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5724350214004517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5420215725898743},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5278246998786926},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5264670848846436},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4952675402164459},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4405374228954315},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33823636174201965},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2132813036441803},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13985782861709595},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413711","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413711","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.05109","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.05109","pdf_url":"https://arxiv.org/pdf/2102.05109","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3128311069","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2102.05109v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2102.05109","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.05109","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/vjm1-h386","is_oa":true,"landing_page_url":"https://doi.org/10.17023/vjm1-h386","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.05109","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.05109","pdf_url":"https://arxiv.org/pdf/2102.05109","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6000000238418579,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3128311069.pdf","grobid_xml":"https://content.openalex.org/works/W3128311069.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1728888090","https://openalex.org/W2086381917","https://openalex.org/W2105921478","https://openalex.org/W2140828385","https://openalex.org/W2163922914","https://openalex.org/W2473388484","https://openalex.org/W2557915412","https://openalex.org/W2737697117","https://openalex.org/W2757519008","https://openalex.org/W2795409001","https://openalex.org/W2796495654","https://openalex.org/W2842511635","https://openalex.org/W2890983311","https://openalex.org/W2892129657","https://openalex.org/W2899775901","https://openalex.org/W2902476877","https://openalex.org/W2940290905","https://openalex.org/W2940385941","https://openalex.org/W2943895317","https://openalex.org/W2946896833","https://openalex.org/W2951974815","https://openalex.org/W2963830550","https://openalex.org/W2964121744","https://openalex.org/W2964287480","https://openalex.org/W2970006822","https://openalex.org/W2971127577","https://openalex.org/W2972394484","https://openalex.org/W2973049979","https://openalex.org/W3002439978","https://openalex.org/W3015829441","https://openalex.org/W3025035610","https://openalex.org/W3034978746","https://openalex.org/W3037057938","https://openalex.org/W3090098535","https://openalex.org/W3096159803","https://openalex.org/W3096656254","https://openalex.org/W3097934054","https://openalex.org/W3097945073","https://openalex.org/W6631190155","https://openalex.org/W6729924827","https://openalex.org/W6756205873","https://openalex.org/W6756824971","https://openalex.org/W6762114000","https://openalex.org/W6767111847","https://openalex.org/W6772622344","https://openalex.org/W6774314701","https://openalex.org/W6777232839","https://openalex.org/W6779919476","https://openalex.org/W6844194202","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W3065827440","https://openalex.org/W3038063545","https://openalex.org/W3176892407","https://openalex.org/W2962785568","https://openalex.org/W2982076115","https://openalex.org/W2954921095","https://openalex.org/W2503793478","https://openalex.org/W2736794749","https://openalex.org/W2790016147","https://openalex.org/W2741158598","https://openalex.org/W3213629100","https://openalex.org/W2923677086","https://openalex.org/W2250676463","https://openalex.org/W3044346681","https://openalex.org/W3081767182","https://openalex.org/W2163738500","https://openalex.org/W3211263893","https://openalex.org/W2501003634","https://openalex.org/W3190275980","https://openalex.org/W2058199791"],"abstract_inverted_index":{"Many":[0],"speech":[1,135],"processing":[2],"methods":[3,139],"based":[4],"on":[5,33,62,75,103],"deep":[6],"learning":[7,86],"require":[8],"an":[9],"automatic":[10],"and":[11,36,52,76,87,137,147],"differentiable":[12],"audio":[13,114],"metric":[14,30,72,132],"for":[15],"the":[16,58],"loss":[17],"function.":[18],"The":[19,79],"DPAM":[20],"approach":[21],"of":[22,49,60,113],"Manocha":[23],"et":[24],"al.":[25],"[1]":[26],"learns":[27],"a":[28,46,110],"full-reference":[29],"trained":[31],"directly":[32],"human":[34,41,50,101,120],"judgments,":[35],"thus":[37],"correlates":[38,117],"well":[39,56,118],"with":[40,119],"perception.":[42],"However,":[43],"it":[44,64],"requires":[45],"large":[47],"number":[48],"annotations":[51],"does":[53],"not":[54],"generalize":[55],"outside":[57],"range":[59,112],"perturbations":[61],"which":[63],"was":[65],"trained.":[66],"This":[67],"paper":[68],"introduces":[69],"CDPAM":[70,116],"\u2013a":[71],"that":[73,129],"builds":[74],"advances":[77],"DPAM.":[78],"primary":[80],"improvement":[81],"is":[82],"to":[83,90,106,109,133],"combine":[84],"contrastive":[85],"multi-dimensional":[88],"representations":[89],"build":[91],"robust":[92],"models":[93],"from":[94],"limited":[95],"data.":[96],"In":[97],"addition,":[98],"we":[99],"collect":[100],"judgments":[102],"triplet":[104],"comparisons":[105],"improve":[107],"generalization":[108],"broader":[111],"perturbations.":[115],"responses":[121],"across":[122],"nine":[123],"varied":[124],"datasets.":[125],"We":[126],"also":[127],"show":[128],"adding":[130],"this":[131],"existing":[134],"synthesis":[136],"enhancement":[138],"yields":[140],"significant":[141],"improvement,":[142],"as":[143],"measured":[144],"by":[145],"objective":[146],"subjective":[148],"tests.":[149]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}